Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2722 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1889. Min Act: -0.0001

Data Index: 380398 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1813. Min Act: -0.0001

Data Index: 398032 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1726. Min Act: -0.0001

Data Index: 103373 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1721. Min Act: -0.0001

Data Index: 546098 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1472. Min Act: -0.0001

Data Index: 457049 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1635. Min Act: -0.0001

Data Index: 388339 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1190538 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1366. Min Act: -0.0001

Data Index: 574051 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1428. Min Act: -0.0001

Data Index: 289995 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1399. Min Act: -0.0001

Data Index: 537469 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1381. Min Act: -0.0001

Data Index: 384318 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1331. Min Act: -0.0001

Data Index: 939087 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1283. Min Act: -0.0001

Data Index: 841541 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1360. Min Act: -0.0001

Data Index: 914442 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1340. Min Act: -0.0001

Data Index: 846390 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1126902 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1333. Min Act: -0.0001

Data Index: 212888 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1324. Min Act: -0.0001

Data Index: 1200039 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1274. Min Act: -0.0001

Data Index: 827313 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.1889. Min Range: -0.1889

Max Act: 0.1271. Min Act: -0.0001

Data Index: 311140 (C4 (Web Text))

Max Activating Token Index: 90